Latest Report (April 27, 2021) | Participation Agreement | API | Validation | Encryption
[Update: March 23, 2021] - The 1:1 matching time limit in Table 1.3 of the API has been updated from 5 milliseconds to 0.1 milliseconds (or 100 microseconds). For developers that cannot meet the new required time limit for matching two templates please contact frvt@nist.gov
All FRVT tracks are open. Algorithms submitted to the FRVT 1:1 track will be run on all the datasets documented in the FRVT 1:1 report. We will additionally run the algorithms on photos in which a face may be occluded to simulate the effect of wearing a protective face mask - see FRVT Face Mask Effects webpage for more information.
[last updated: April 27 , 2021]
| 2017 | 2018 | 2019 | 2020 | 2021 | Total | |
|---|---|---|---|---|---|---|
| Number of algorithms | 58 | 101 | 167 | 140 | 70 | 536 |
| Number of unique developers | 31 | 50 | 109 | 105 | 70 | 205 |
[last updated: April 27, 2021]
The table shows the top performing 1:1 algorithms measured on false non-match rate (FNMR) across several different datasets. FNMR is the proportion of mated comparisons below a threshold set to achieve the false match rate (FMR) specified. FMR is the proportion of impostor comparisons at or above that threshold. The algorithms are ordered initially in terms of lowest mean rank across four datasets, calculated using FNMR @ FMR = 10-5 DT>=12YRS MUGSHOT, and FNMR @ FMR = 10-6 for the VISA, VISABORDER and BORDER datasets. This rewards broad accuracy over a good result on one particular dataset. For algorithms with missing FNMR values, the FNMR value is 1.0, and the rank is a big number (~the number of algorithms in the table). The rows for a given column may be sorted by clicking on its header.
Algorithms submitted to FRVT implement NIST’s application programming interface (API). We measure the duration of all function calls using the C++ std::chrono::high resolution clock on an unloaded server-class machine. The table below includes durations of the template generation, finalization, search calls. In addition the size of the algorithm is reported in two parts: the recognition models, and the libraries.
Additional algorithms not listed in the table can be found in Table 2 of our latest FRVT report. It is a draft made available for comments. It will be updated on a monthly basis as algorithms and computations complete, as datasets are added, and as new analyses are developed.FRVT is conducted by NIST, an agency of the United States Government. Participation is free of charge. FRVT is open to a global audience of face recognition developers. All organizations who seek to participate in FRVT must sign and submit all pages of this Participation Agreement by mail AND send a PDF scanned copy to frvt@nist.gov. [last update: 2020-06-15]
Note: In addition to the terms of the Participation Agreement 1) all correspondence from the provider to NIST must come from an organizational email address of the participating entity – no generic emails from gmail.com, mail.ru, qq.com, etc. will be accepted; 2) the point of contact listed in the participation agreement must specify an organizational email address; 3) the organization must have a non-trivial web presence. [last update: 2018-01-09]
A new API document has been published. All FRVT APIs reference the supporting FRVT General Evaluation Specifications, which includes hardware and operating system environment, software requirements, reporting, and common data structures that support the APIs. [last update: 2021-03-22]
An updated validation package has been published. All participants must run their software through the updated validation package prior to submission. The purpose of validation is to ensure consistent algorithm output between your execution and NIST’s execution. Note: The provider identifier in the core implementation library must be an appropriate, representative, non-infringing name of the main provider of the software. If the provider identifier is not representative of the submitting organization, NIST reserves the right to reject the submission for testing. [last update: 2020-09-10]
All submissions must be properly encrypted and signed before transmission to NIST. This must be done according to these instructions using the FRVT Ongoing public key linked from this page. Participants must email their public key to NIST. The participant’s public key must correspond to the participant’s public-key fingerprint provided on the signed Participation Agreement. [last update: 2017-09-11]